The applications of mixtures of normal distributions on empirical finance: A selected survey

Abstract

This paper provides a selected review of the recent developments and applications of mixtures of normal (MN) distribution models in empirical finance. One attractive property of the MN model is that it is flexible enough to accommodate various shapes of continuous distributions, and able to capture leptokurtic, skewed and multimodal characteristics of financial time series data. In addition, the MN-based analysis fits well with the related regime-switching literature. The survey is conducted under two broad themes: (1) minimum-distance estimation methods, and (2) financial modeling and its applications.